Preprint
Aug 2026
DAPD: Dual-Anchored Policy Distillation
DAPD is proposed, a unified framework with two levels of anchoring that significantly alleviates privilege illusion, outperforming OPSD on Qwen3-4B by +2.00 points on average across tasks.
Jianyu Wu, Yizhou Wang, Encheng Su et al.
· 0 citations